No abstract

The use of renewable energy sources is one way to decarbonize current energy consumption. In this context, photovoltaic (PV) technology plays a direct fundamental role since it can convert sun irradiance into electricity to be used for supplying electric loads for households. Despite the huge availability of the solar resource, the intermittence of PV production may reduce its exploitation. This problem can be solved by the introduction of storage systems, such as batteries, storing electricity when PV overproduction occurs and acting as a source when PV generation is absent. Consequently, increase in self-sufficiency and self-consumption can be expected in residential end users, paving the way for more sustainable energy systems. In this paper, an economic, energy, and environmental analysis of PV systems (without and with batteries) for the household is performed for the whole of Italy, by means of a Geographical Information Systems (GIS) approach. A model to simulate energy balance and to manage batteries is defined for households to assess the profitability of such systems under an Italian regulation framework. Concerning results, indicators are provided at a national scale using GIS tools to highlight areas where investments are more profitable, boosting the CO2 emission reduction.

Purpose This paper aims to compare stochastic gradient method used for neural network training with global optimizer without use of gradient information, in particular differential evolution. Design/methodology/approach This contribute shows the application of heuristic optimization algorithms to the training phase of artificial neural network whose aim is to predict renewable power production as function of environmental variables such as solar irradiance and temperature. The training problem is cast as the minimization of a cost function whose degrees of freedom are the parameters of the neural network. A differential evolution algorithm is substituted to the more usual gradient-based minimization procedure, and the comparison of their performances is presented. Findings The two procedures based on stochastic gradient and differential evolution reach the same results being the gradient based moderately quicker in convergence but with a lower value of reliability, as a significant number of runs do not reach convergence. Research limitations/implications The approach has been applied to two forecasting problems and, even if results are encouraging, the need for extend the approach to other problems is needed. Practical implications The new approach could open the training of neural network to more stable and general methods, exploiting the potentialities of parallel computing. Originality/value To the best of the authors’ knowledge, the research presented is fully original for the part regarding the neural network training with differential evolution.

No abstract